1
SRI SIDDHARTHA INSTITUTE OF TECHNOLOGY, TUMAKURU
(A Constituent College of Sri Siddhartha Academy of Higher Education)
Department of Medical Electronics
VII SEMESTER SCHEME
(2016-17 Scheme)
Sl Sub.Code Name of Subject LH T PR S C
1 ML7T01 Biomedical Digital Signal
Processing 4 0 0 0 4
2 ML7T02 Principles of Medical Imaging 4 0 0 0 4
3 ML7T03 IoT and smart sensors 3 0 0 1 4
4 ML7PE42X Elective II 3 0 0 0 3
5 ML7PE53X Elective III 3 0 0 0 3
6 ML7L01 BMDSP Lab 0 0 3 0 1.5
7 ML7L02 C++ and Python Lab 0 0 3 0 1.5
8 ML7PW01 Project Work 0 8 0 4
Total 18 00 14 01 25
LH=Lecture Hour T = Tutorial Hour
XX = CV/ ME/ EE/ EC/ CS/ PR= Practical Hour
OE= Open Elective S=Self-study Hour
Q = 1/2/3/ C= Credit
R = 1/2/3/
L = Laboratory PW = Project Work
Elective –II Credits 3-0-0-3
Sub.Code Name of the Subject Sub.Code Name of the Subject
ML7PE421 Artificial Organs and
Biomaterials ML7PE423
Linear Algebra and its
applications in medicine
ML7PE422 Adaptive Signal Processing ML7PE424 Brain Computer Interface
Elective –III Credits 3-0-0-3
Sub.Code Name of the Subject Sub.Code Name of the Subject
ML7PE531 Pattern Recognition in Medicine ML7PE533 Ergonomics and
Rehabilitation Engineering
ML7PE532 Biometrics ML7PE534 Artificial Intelligence
2
SRI SIDDHARTHA INSTITUTE OF TECHNOLOGY, TUMAKURU
(A Constituent College of Sri Siddhartha Academy of Higher Education)
Department of Medical Electronics
VIII SEMESTER SCHEME
(2016-17 Scheme)
Sl.
No.
Sub.Code Name of Subject LH T PR S C
1 ML8T01 Neural Networks 4 0 0 0 4
2 ML8T02 Biomedical Therapeutic Equipments 4 0 0 0 4
3 ML8PE3X Elective IV 3 0 0 0 3
4 ML8PE4X Elective V 3 0 0 0 3
5 ML8PW02 Project Work 2 4 12 0 10
6 ML8TS01 Technical Seminar 0 0 0 1 1
Total 16 04 12 01 25
LH=Lecture Hour T = Tutorial Hour
XX = CV/ ME/ EE/ EC/ CS/ PR= Practical Hour
OE= Open Elective S=Self-study Hour
Q = 1/2/3/ numerals C= Credit
R =1/2/3
L = Laboratory PW = Project Work
TS=Technical Seminar
Elective –IV Credits 3-0-0-3
Sub.Code Name of the Subject
ML8PE311 Speech Signal Processing
ML8PE312 Smart Wearable Systems
ML8PE313 Machine Learning
ML8PE314 Clinical Data Analytics
Elective –V Credits 3-0-0-3
Sub.Code Name of the Subject
ML8PE411 ARM Processors
ML8PE412 Robotics and Automation
ML8PE413 Medical Device Development
ML8PE414 Virtual BMI
3
BIOMEDICAL DIGITAL SIGNAL PROCESSING
Subject Code: ML7T01 Credits: 4-0-0-4
Duration: 4 Hr/Week No. of Hrs: 52Hrs.
Course Objectives:
• This course helps to understand the nature and difficulties to acquire bio-signal and its
processing concepts for analysis.
• It also helps to bring out the concepts related Neurological signal processing and Sleep
disorder.
• Explains the concept of data compression techniques.
• Emphasizes on Signal averaging, adaptive filers and its applications.
UNIT I: [11 Hrs]
Introduction to Biomedical Signals: The nature of biomedical signals, the action potential,
objectives of biomedical signal analysis, Difficulties in biomedical signal analysis, computer
aided diagnosis.
Neurological signal processing: The brain and its potentials, The electrophysiological origin of
brain waves, The EEG signal and its characteristics, EEG analysis.
UNIT II: [11 Hrs]
ECG Signal Processing: ECG data acquisition, ECG lead system, ECG parameters and their
estimation, ECG QRS detection techniques: Template matching, differentiation based QRS
detection techniques. Estimation of R-R Interval: Finite first difference method. The use of
multi-scale analysis for parameter estimation of ECG waveforms, Arrhythmia analysis
monitoring, long term continuous ECG recording.
UNIT III: [08 Hrs]
Sleep EEG: Data acquisition and classification of sleep stages, The Markov model and Markov
chains, Dynamics of sleep-wake transitions, Hypnogram model parameters, event history
analysis for modeling sleep.
UNIT IV: [10 Hrs]
Ecg Data Reduction Techniques: direct data compression techniques, direct ECG data
compression techniques: Turing point algorithm, AZTEC algorithm and FAN algorithm, other
data compression techniques: data compression by DPCM, data compression method
4
comparison.
UNIT V: [12 Hrs]
Signal Averaging: Basics of signal averaging, signal averaging as a digital filter, a typical
averager.
Adaptive Filters: Principle of an adaptive filter, the steepest descent algorithm, adaptive noise
canceller: (a)cancellation of 60 Hz interference in electrocardiography, (b) Canceling donor-
heart interference in heart-transplant electrocardiography, (c)Cancellation of ECG signal from
the electrical activity of the chest muscles, (d)canceling of maternal ECG in fetal ECG,
(e)Cancellation of High frequency noise in Electro-surgery.
Text Books:
1. Biomedical Digital Signal Processing, Willis J. Tompkins, PHI.
2. Biomedical Signal Processing- principles and techniques by D. C. Reddy, Tata McGraw-
Hill, 2005
3. Biomedical Signal Analysis by Rangaraj M. Rangayyan, IEEE Press, 2001.
Reference Book:
1. Biomedical Signal Processing -Akay M, , Academic: Press 1994
2. Biomedical Signal Processing -Cohen.A, -Vol. I Time & Frequency Analysis, CRC
Press, 1986.
Course Outcomes: On completion of the course the student can recall
1. Understand the origin of EEG signals and their characteristics.
2. Understand the origin of ECG signals and their characteristics.
3. Understand the processing techniques required to analyze the bio medical signals
4. Understand data reduction techniques for ECG signal.
PRINCIPLES OF MEDICAL IMAGING
Subject Code: ML7T02 Credits: 4-0-0-4
Duration: 4 Hr/Week No. of Hrs: 52 Hrs
Course Objectives:
• Build the physics background of interaction of radiation with matter, enabling
participants to understand projection radiography, mammography, and fluoroscopy and
5
train them to assess image distortions, image attenuation for x‐ray radiography systems.
• Expose students to the developments in X‐ray Computed Tomography leading to
modern day multi‐slice, helical CT scanners and introduce the concept of computed
tomography reconstruction.
• Divulge the image formation, image quality, and imaging hardware for ultrasound
scanning. Explain the imaging principles and derive the fundamental equation of MRI.
• Expose the participants to advanced MR techniques including fast spin echoes, MR
angiography, echo planar imaging, magnetization prepared sequences, diffusion and
perfusion theory and sequences.
UNIT I:[11 Hrs]
X-rays: Introduction to Electromagnetic Spectrum, Fundamentals of X-Rays, Generation and
Detection of X-Rays, X-ray Diagnostic Methods.
UNIT II:[10 Hrs]
X-Rays: Recent Developments, X-ray Imaging Characteristics, Biological effects of Ionizing
radiation.
UNIT III:[10 Hrs]
Ultrasound: Fundamentals of Acoustic Propagation, Generation and Detection of Ultrasound,
Ultrasonic Diagnostics Methods, New Developments, Image Characteristics, Biological effects
of Ultrasounds.
UNIT IV:[11 Hrs]
Radionuclide Imaging: Fundamentals of Radioactivity, Generation and Detection of nuclear
emission, Diagnostic methods using radiation detector probes, Radionuclide Imaging Systems,
New Radionuclide Imaging methods, Characteristics of Radionuclide Images, Internal radiation
dosimeter and biological effects.
UNIT V: [10 Hrs]
Magnetic Resonance Imaging
Fundamentals of nuclear magnetic resonance, Generation and Detection of NMR signal, Imaging
Methods, In vivo NMR Spectroscopy, Characteristics of MRI, Biological Effects of Magnetic
Fields.
6
Text Books:
1. Shung K. Kirk, Tsui Benjamin, Smith.B.Michael, “Principles of Medical Imaging”..
2. Suetens Paul, “Fundamentals of Medical Imaging” Cambridge University Press, 2002.
Reference Book:
1. Khandpur R.S. “Handbook of Biomedical Instrumentation”, 2nd Ed., Tata-McGRaw Hill,
2003.
Course Outcomes: On the completion of the course the students shall be able
• To gain knowledge on X-rays and its generation.
• To understand and distinguish different diagnostic method.
• To explain concepts of CT, Projection functions of CT.
• Understand the principles of Radionuclide imaging and Magnetic resonance imaging.
IoT and SMART SENSORS
Subject Code: ML7T03 Credits: 3-0-1-4
Duration: 3Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
• Understand the purpose of measurement, the methods of measurements, errors associated
with measurements.
• Know the principle of transduction, classifications and the characteristics of different•
transducers and study its biomedical applications.
UNIT I: [08 Hrs]
Introduction to IoT: Definition & Characteristics of IoT, Physical Design of IoT, Logical
Design of IoT, IoT Enabling Technologies, IoT Levels.
7
UNIT II: [08 Hrs]
IoT System Management: Introduction, Machine-to-Machine (M2M), Difference between IoT
and M2M, SDN and NFV for IoT, Need for IoT System Management, SNMP, Network Operator
Requirements, NETCONF, YANG, IoT Systems Management with NETCONF-YANG.
UNIT III: [07 Hrs]
Domain Specific IoTs: Applications, Home Automation, Cities, Environment, Energy, Retail,
Logistics, Agriculture, Industry, health & Lifestyle.
UNIT IV: [08 Hrs]
Smart Sensors, Signal Conditioning and Control: Introduction, Smart Sensor Model,
SLEEPMODETM Operational Amplifiers, Rail – to – Rail Operational Amplifiers, Switched
Capacitor Amplifier, 4 – to 20 mA Signal Transmitter, Analog to Digital Converter, MCU
control, Modular MCU Design, DSP control.
UNIT V: [07 Hrs]
Protocols and Standards for Smart Sensors: CAN protocol, CAN Module, Neuron Chips,
MCU Protocols, IEEE 1451 working relationship, IEEE 1451.1, IEEE 1451.2, IEEE P1451.3,
IEEE P1451.4.
Text Books:
1. Internet of Things – A hands-on approach, Arshdeep Bahga and Vijay Madisetti,
Universities Press (India) Private Ltd., 2015
2. Understanding Smart Sensors, Randy Frank, 2nd Edition, Artech House Publications,
2000.
REFERENCE BOOKS:
1. Rethinking the Internet of Things: A Scalable Approach to Connecting Everything, Francis
daCosta and Byron Henderson, Apress Open, Intel Publication. 2014
2. Learning Internet of Things, Peter Waher, PACKT Publishing, 2015
3. Smart Sensor Systems, Gerard Meijer, John – Wiley and Sons, 2008.
Course Outcomes: on the completion of this course the student will be able to
1. Explain the basic design and requirement of IoT.
2. Identify the importance of different types of protocols and models used with IoT.
3. Analyze the requirements of components of smart sensors.
8
4. Determine the importance of communication protocol and standards that is used with
smart sensors and improve the functionality of conventional systems using IoT.
ARTIFICIAL ORGANS AND BIOMATERIALS
Subject Code: ML7PE421 Credits: 3-0-0-3
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
• To create awareness to the student with modern artificial organs devices and methods
used to partially support or completely replace pathological organ
• Understand the design and working of artificial heart, kidney, and blood.
• To know about working of heart valve. Design of artificial heart valve
• Study about biomaterial which is used for design of artificial organ. Understand the
characteristics of polymeric and metallic biomaterial.
UNIT I: [07 Hrs]
ARTIFICIAL ORGANS: INTRODUCTION: Substitutive medicine, outlook for organ
replacement, design consideration, evaluation process.
ARTIFICIAL HEART AND CIRCULATORY ASSIST DEVICES: Engineering design,
Engg design of artificial heart and circulatory assist devices.
UNIT II: [07 Hrs]
ARTIFICIAL KIDNEY: Functions of the kidneys, kidney disease, renal failure, renal
transplantation, artificial kidney, dialyzers, and membranes for haemodialysis, haemodialysis
machine, peritoneal dialysis equipment-therapy format, fluid and solute removal.
ARTIFICIAL BLOOD: Artificial oxygen carriers, fluorocarbons, hemoglo bin for oxygen
carrying plasma expanders, hemoglobin based artificial blood.
UNIT III: [08 Hrs]
ARTIFICIAL LUNGS: Gas exchange systems, Cardiopulmonary bypass (heart-lung machine)-
principle, block diagram and working, artificial lung versus natural lung.
CARDIAC VALVE PROSTHESES: Mechanical valves, tissue valves, current types of
prostheses, tissue versus mechanical, engineering concerns and hemodynamic assessment of
9
prosthetic heart valves, implications for thrombus deposition, durability, current trends in valve
design.
UNIT IV: [08 Hrs]
CERAMIC BIOMATERIALS: Introduction, non absorbable/relatively bioinert bioceramics,
biodegradable/restorable ceramics, bioreactive ceramics, deterioration of ceramics, bioceramic-
manufacturing techniques
POLYMERIC BIOMATERIALS: Introduction, polymerization and basic structure, polymers
used as biomaterials, sterilization, surface modifications to for improving biocompatibility.
UNIT V: [09 Hrs]
BIOMATERIALS: Introduction to biomaterials, uses of biomaterials, biomaterials in organs &
body systems, materials for use in the body, performance of biomaterials.
METALLIC BIOMATERIALS: Introduction, Stainless steel, Cobalt-Chromium alloy,
Titanium alloys, Titanium-Nickel alloys, Dental metals, Corrosion of metallic implants,
Manufacturing of implants.
Text Books:
1. Biomedical Engineering Handbook-Volume1 (2nd Edition) by J.D.Bronzino (CRC Press /
IEEE Press, 2000).
2. Biomedical Engineering Handbook-Volume 2 (2nd Edition) by J.D.Bronzino (CRC Press
/ IEEE Press, 2000)
3. Handbook of Biomedical Instrumentation (2nd Edition) by R.S.Khandpur (Tata McGraw
Hill, 2003)
Course Outcomes: on the completion of this course the student will be able to
• Understand the need of artificial organs.
• Understand the function of various organs in your body.
• Learn about the design of the various artificial organs using biomaterial.
• Understand the various biomaterials.Learn composite, biodegradable polymeric and
tissue derived materials.
LINEAR ALGEBRA AND ITS APPLICATIONS IN MEDICINE
Subject Code: ML7PE423 Credits: 3-0-0-3
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
10
Course Objectives:
Solve systems of linear equations using various methods including Gaussian and GaussJordan
elimination and inverse matrices. Perform matrix algebra, invertibility, and the transpose and
understand vector algebra in Rn . Determine relationship between coefficient matrix invertibility
and solutions to a system of linear equations and the inverse matrices. Find the dimension of
spaces such as those associated with matrices and linear transformations.
UNIT I: [09 Hrs]
Linear equations: Fields; system of linear equations, and its solution sets; elementary row
operations and echelon forms Matrix operations; invertible matrices, LU-factorization.
Vector spaces: Vector spaces; subspaces; bases and dimension; coordinates; summary of row-
equivalence; computations concerning subspaces.
UNIT II: [08 Hrs]
Linear Transformations: Linear transformations; algebra of linear transformations;
isomorphism; representation of transformations by matrices; transpose of a linear transformation.
UNIT III: [07 Hrs]
Canonical Forms: Characteristic values; invariant subspaces; direct-sum decompositions;
invariant direct sums; primary decomposition theorem; cyclic bases; Jordan canonical form.
UNIT IV: [08 Hrs]
Inner Product Spaces: Inner products; inner product spaces; orthogonal sets and projections.
UNIT V: [07 Hrs]
Gram-Schmidt process; QR-factorization; least-squares problems; unitary operators
Symmetric Matrices and Quadratic Forms: Digitalization; quadratic forms; constrained
Optimization; singular value decomposition.
Text Books:
1. Gilbert Strang, "Linear Algebra and its Applications", 4thEdition, Thomson Learning Asia,
2007.
2. David C. Lay, "Linear Algebra and its Applications", 3rd Edition, Pearson Education (Asia)
Pvt. Ltd, 2005.
3. Bernard Kolman and David R. Hill, "Introductory Linear Algebra with Applications,"
11
Pearson Education (Asia) Pvt. Ltd, 7th edition, 2003.
Course Outcomes:
• Understand LU factorization and elements of vector spaces.
• Learn linear transformations and least square approximations to solve inconsistent
systems, Orthonormal vectors using Gram-Schmidtt process and QR factorization.
• Understand concepts in Eigen spaces and its applications
• Understand the concept of probability, distributions and its application in Biology and
medical Science.
ADAPTIVE SIGNAL PROCESSING
Subject Code: ML7PE422 Credits: 3-0-0-3
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
UNIT I: [08 Hrs]
ADAPTIVE SYSTEMS: Definition and characteristics, Areas of application, general properties, open
and close loop adaptation, Application closed loop adaptation, examples of adaptive systems. The
adaptive linear combiner: General description, input signal and weight vectors, desired response and
error, the performance function gradient and minimum mean square error. Example of a performance
surface, alternative expression of the gradient, De correlation of error and input components.
UNIT II: [08 Hrs]
PROPERTIES OF QUADRATIC PERFORMANCE SURFACE: Normal form of input correlation
Matrix, Eigen and eigen vectors of the input correlation matrix. An example with two weights,
geometrical significance of Eigen vectors and Eigen values.
UNIT III: [08 Hrs]
SEARCHING THE PERFORMANCE SURFACE: Methods of searching the performance surface.
Basic idea of gradient search methods, A simple gradient search algorithm and its solution.
UNIT IV: [09 Hrs]
SEARCHING THE PERFORMANCE SURFACE: Methods of searching the performance surface.
Basic idea of gradient search methods, A simple gradient search algorithm and its solution. Stability and
rate of convergence, the learning curve, Gradient search by Newton’s method in multi dimensional space,
12
gradient search by the method of steepest descent, comparison of learning curves.
UNIT V: [06 Hrs]
GRADIENT ESTIMATION AND EFFECTS ON ADAPTATION: Gradient component estimation by
derivatives measurements, the performance penalty, derivative measurement and performance penalties
with multiple weights.
Text Books:
1. Adaptive signal Processing- B. Widrow & S D Streans, Pearson Education 1985.
Reference Books:
1.Adaptive filters-C F N Cowan & P M Grant, Prentice Hall, 1985.
Course Outcomes:
• Describe optimal minimum mean square estimators and in particular linear estimators.
• Hypothesize Wiener filters (FIR, non-causal, causal) and evaluate their performance.
• Apply combination of theory and software implementations to solve adaptive signal problems.
• Identify applications in which it would be possible to use the different adaptive filtering
approaches.
BRAIN COMPUTER INTERFACE
Subject Code: ML7PE424 Credits: 3-0-0-3
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
This course aims for students to
(1) obtain the background to understand brain-computer interaction and human-computer
interaction; (2) understand the literature in the field of brain sensing for human-computer
interaction research; (3) understand the various tools used in brain sensing, with a focus on
functional near-infrared spectroscopy (fNIRS) research at Drexel.
(4) Understand the steps required to use real-time brain sensing data as input to an interactive
system.
(5) understand the domains and contexts in which brain-computer interfaces may be effective;
(6) Understand the open questions and challenges in brain-computer interaction research today.
13
UNIT I: [08 Hrs]
Basic Neurosciences: Basic Neuroscience: Neurons, Action Potentials or Spikes, Dendrites and
Axons, Synapses, Spike Generation, Adapting the Connections: Synaptic Plasticity – (LTP,
LTD, STDP, Short-Term Facilitation and Depression), Brain Organization, Anatomy, and
Function.
Recording and Stimulating the Brain: Recording Signals from the Brain: Invasive Techniques
&Noninvasive Techniques. Stimulating the Brain - Invasive Techniques & nonTechniques.
Simultaneous Recording and Stimulation: Multi-electrode Arrays, Neurochip.
UNIT II: [08 Hrs]
Signal Processing for BCI's: Spike Sorting, Frequency Domain Analysis: Fourier analysis,
Discrete Fourier Transform (DFT), Fast Fourier Transform (FFT), Spectral Features, Wavelet
Analysis. Time Domain Analysis: Hjorth Parameters , Fractal Dimension , Autoregressive (AR)
Modeling, Bayesian Filtering, Kalman Filtering, Particle Filtering), Spatial Filtering : (Bipolar,
Laplacian, and Common Average Referencing ,Principal Component Analysis (PCA)
,Independent Component Analysis (ICA) , Common Spatial Patterns (CSP) 73 Artifact
Reduction Techniques: Thresholding, Band-Stop and Notch Filtering, Linear Modeling,
Principal Component Analysis (PCA), Independent Component Analysis (ICA).
UNIT III: [08 Hrs]
Building a BCI: Major Types of BCIs: Brain Responses Useful for Building BCIs:Conditioned
Responses, Population Activity, Imagined Motor and Cognitive Activity, Stimulus-Evoked
Activity.
Invasive BCIs: Two Major Paradigms in Invasive Brain-Computer Interfacing: BCIs Based on
Operant Conditioning, BCIs Based on Population Decoding.
UNIT IV: [09 Hrs]
Invasive BCIs in Humans: Cursor and Robotic Control Using a Multielectrode Array Implant,
Cognitive BCIs in Humans, Long-Term Use of Invasive BCIs, Long-Term BCI Use and
Formation of a Stable Cortical Representation, Long-Term Use of a Human BCI Implant
Semi-Invasive BCIs:Electrocorticographic (ECoG) BCIs -ECoG BCIs in Animals, ECoG BCIs
in Humans, BCIs Based on Peripheral Nerve Signals Nerve-Based BCIs, Targeted Muscle
Innervations (TMR).
Non-Invasive BCIs:Oscillatory Potentials and ERD, Slow Cortical Potentials, Movement
14
Related Potentials, Stimulus Evoked Potentials; BCIs Based on Cognitive Tasks, Error Potentials
in BCIs, Co-adaptive BCIs, Hierarchical BCIs.
Other Noninvasive BCIs: fMRI, MEG, and fNIR: Functional Magnetic Resonance Imaging
Based BCIs, Magneto encephalography Based BCIs, Functional Near Infrared and Optical BCIs.
BCIs that Stimulate: Sensory Restoration, Restoring Hearing: Cochlear Implants, Restoring
Sight: Cortical and Retinal Implants, Motor Restoration, Deep Brain Stimulation (DBS), Sensory
Augmentation.
UNIT V: [06 Hrs]
Medical Applications: Sensory Restoration, Motor Restoration, Cognitive Restoration,
Rehabilitation, Restoring Communication with Menus, Cursors, and Spellers, Brain Controlled
Wheelchairs
Nonmedical Applications: Web Browsing and Navigating Virtual Worlds, Robotic Avatars,
High Throughput Image Search Lie Detection and Applications in Law , Monitoring Alertness,
Estimating Cognitive Load, Education and Learning, Security, Identification, and
Authentication, Physical Amplification with Exoskeletons, Mnemonic and Cognitive
Amplification , Applications in Space, Gaming and Entertainment, Brain-Controlled Art.
Ethics of Brain-Computer Interfacing: Medical, Health, and Safety Issues, Balancing Risks
versus Benefits, Informed Consent, Abuse of BCI Technology, BCI Security and Privacy, Legal
Issues, Moral and Social-Justice Issues.
Text Books:
[1] Brain-Computer Interfacing: An Introduction (1 Edition) by Rajesh P. N. Rao
[2] Brain-Computer Interfaces: Revolutionizing Human-Computer Interaction (The Frontiers
Collection) Hardcover – (13 Dec 2010) by Bernhard Graimann (Editor), Brendan Z. Allison
(Editor), GertPfurtscheller (Editor)
Course Outcomes:
• Apply the knowledge of mathematics science and engineering fundamentals to
understand the Brain Organization.
• Apply the knowledge of mathematics science and engineering fundamentals to
understand the brain anatomy and Function.
• Analyze and process the brain signals for artifact reduction.
• Understand types of BCI, principles and its applications which are present state of art in
the Neurosciences domain.
15
PATTERN RECOGNITION IN MEDICINE
Subject Code: ML7PE531 Credits: 3-0-0-3
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
Pattern recognition techniques are used to design automated systems that improve their own
performance through experience. This course covers the methodologies, technologies, and
algorithms of statistical pattern recognition from a variety of perspectives. Topics including
Bayesian Decision Theory, Estimation Theory, Linear Discrimination Functions, Nonparametric
Techniques, Decision Trees, and Clustering Algorithms etc. will be presented.
UNIT I: [08 Hrs]
Introduction: Machine perception, pattern Recognition systems, Design cycles, learning and
adaptation.
Probability: Random variable, joint distribution and densities, moments of random variable,
Estimation of parameters from sample.
UNIT II: [08 Hrs]
Statistical decision making: Introduction, Baye’s theorem, multiple features, conditionally
independent features, decision bounderies, unequal costs of error, estimation of error rates,
characteristic curves, problems. (3.1-3.7, 3.9 from text 1).
UNIT III: [08 Hrs]
Non parametric Decision making: Introduction, Histograms, kernel and window estimators,
nearest neighbor classification techniques, adaptive decision boundaries, adaptive discriminate
functions, minimum squared error discriminant functions. (4.1-4.7 text 1)
UNIT IV: [07 Hrs]
Clustering: Introduction, Hierarchical clustering, partitional clustering, Unsupervised Bayesion
learning, Hierarchical clustering, partitional clustering, problems.
UNIT V: [08 Hrs]
Processing of waveforms and images: Introduction, gray level scaling transformations,
equalization, geometric image scaling and interpolation, edge detection, laplacian and sharpening
operators, line detection and template matching, logarithmic gray level scaling. (7.1-7.9 text 1)
16
Text Books:
1. Pattern Recognition and Iamge Analysis, Earl Gose, Richard Johnson Baugh and Steve
jost, PHI
Reference Book:
1. Richard O.Duda, Peter E.Herd and David & Stork, pattern classification, john Wiley
and sons, Inc 2nd Ed.2001.
2. Robert Schlkoff, Pattern Recognition: Statistical Structural and Neural Approaches,
John Wiley and sons, Inc, 1992.
Course Outcomes:
• Understand the basic concepts of Pattern Recognition and its applications
• Apply the concepts of joint distribution & densities and risk estimators of events.
• Understand Statistical decision making and Non parametric decision making
• Understand the concepts of clustering - hierarchical clustering and partitional clustering
and analysis of wave forms and Image.
BIOMETRICS
Subject Code: ML7PE532 Credits: 3-0-0-3
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
• To understand the state-of-the-art in biometric technologies;
• To survey the currently available biometric systems;
• To explore ways to improve some of the current techniques;
• To learn and implement some of the biometrics authentication;
• To explore new techniques
UNIT I: [08 Hrs]
Introduction – Benefits of biometric security – Verification and identification – Basic working of
biometric matching – Accuracy – False match rate – False non-match rate – Failure to enroll rate
– Derived metrics – Layered biometric solutions.
17
UNIT II: [08 Hrs]
Finger scan – Features – Components – Operation (Steps) – Competing finger Scan technologies
– Strength and weakness. Types of algorithms used for interpretation. Voice Scan - Features –
Components – Operation (Steps) – Competing voice Scan (facial) technologies – Strength and
weakness.
UNIT III: [08 Hrs]
Iris Scan - Features – Components – Operation (Steps) – Competing iris Scan technologies –
Strength and weakness. Facial Scan - Features – Components – Operation (Steps) – Competing
facial Scan technologies – Strength and weakness.
UNIT IV: [07 Hrs]
Other physiological biometrics – Hand scan – Retina scan – AFIS (Automatic Finger Print
Identification Systems) – Behavioral Biometrics – Signature scan- keystroke scan.
UNIT V: [08 Hrs]
Biometrics Application – Biometric Solution Matrix – Bio privacy – Comparison of privacy
factor in different biometrics technologies – Designing privacy sympathetic biometric systems.
Biometric standards – (BioAPI , BAPI) – Biometric middleware. Biometrics for Network
Security: Statistical measures of Biometrics. Biometric Transactions.
Text Books:
1. Biometrics–Identity Verification in a Networked World–Samir Nanavati, Michael Thieme,
Raj Nanavati, Wiley India Pvt Ltd, 2002 .
2. Biometrics for Network Security- Paul Reid, Pearson Education, 2004.
Reference Book:
1. Biometrics- The Ultimate Reference- John D. Woodward, Jr. Wiley Dreamtech.
2. Biometric Systems Technology, Design and Performance Evaluation, James Wayman, Anil
Jain, Davide Maltoni and Dario Maio, Springer Publications.
3. Personal Identification in Networked Society, Jain, A.K.; R Bolle, Ruud M.; S Pankanti,
Sharath, 1st ed. 1999. 2nd printing, 2006, Springer Publications.
4. Handbook of Biometrics, Jain, Anil K.; Flynn, Patrick; Ross, Arun A, Springer, 2008.
Course Outcomes:
• Understand the fundamentals and the need of biometrics.
18
• Learn the deployment, strength & weakness of the types of Biometrics.
• Learn the uncommon biometrics and its usage.
• Understand the applications of Biometrics and learn the risks, standards and testing /
Evaluation process of Biometrics.
ERGONIMICS AND REHABILITATION ENGINEERING
Subject Code: ML7PE533 Credits: 3-0-0-3
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
This course covers the use of ergonomic principles to recognize, evaluate, and control workplace
conditions that cause or contribute to musculoskeletal and nerve disorders. Course topics include
work physiology, anthropometry, musculoskeletal disorders, use of video display terminals, and
risk factors such as vibration, temperature, material handling, repetition, and lifting and patient
transfers in health care. Course emphasis is on industrial case studies covering analysis and
design of work stations and equipment workshops in manual lifting, and coverage of current
OSHA compliance policies and guidelines.
UNIT I: [08 Hrs]
Introduction : Focus of ergonomics & its applications, Body mechanics: Basics, Anatomy of
Spine & pelvis related to posture, postural stability & adaptation, Low back pain, risk factors
formusculo skeletal disorders in workplaces, Anthropometric principles in workspace: Designing
for a population of users, Human variability sources, applied anthropometry in ergonomics &
design, anthropometry & personal space.
UNIT II: [07 Hrs]
Design of Repetitive Tasks: Work related musculoskeletal disorders, injuries to upper body at
work, neck disorders, carpal tunnel syndrome, tennis elbow, shoulder disorder, ergonomic
interventions. Design of physical environment: human thermoregulation, thermal environment,
working in hot & cold climates, skin temperature, protection against extreme climates, comfort
& indoor climate, ISO standards.
UNIT III: [08 Hrs]
Engineering Concepts in Rehabilitation Engineering: Anthropometry: Methods for Static and
dynamic Measurements: Area Measurements, Measurement of characteristics and movement,
19
Ergonomic aspects in designating devices: Introduction to Models in Process Control, Design of
Information Devices, Design of Controls Active Prostheses: Active above knee prostheses.
Myoelectric hand and arm prostheses- different types, block diagram, signal flow diagram and
functions. The MARCUS intelligent Hand prostheses.
UNIT IV: [08 Hrs]
engineering concepts in sensory rehabilitation engineering: Sensory augmentation and
substitution: Visual system: Visual augmentation, Tactual vision substitution, and Auditory
vision substitution. Auditory system: Auditory augmentation, Audiometer, Hearing aids,
cochlear implantation, visual auditory substitution, tactual auditory substitution, Tactual system:
Tactual augmentation, Tactual substitution.
UNIT V: [08 Hrs]
Orthopedic Prosthetics and Orthotics in rehabilitation: Engineering concepts in motor
rehabilitation, applications. Computer Aided Engineering in Customized Component Design.
Intelligent prosthetic knee, A hierarchically controlled prosthetic and A self-aligning orthotic
knee joint. Externally powered and controlled Orthotics and Prosthetics. FES systems-
Restoration of hand function, restoration of standing and walking, Hybrid Assistive Systems
(HAS).
Text Books:
1. Introduction to Ergonomics by R S Bridger, Rout ledge Taylor & Francis group,
London,2008 2. Bronzino, Joseph; Handbook of biomedical engineering.
2. 2nd edition, CRC Press, 2000. 24 3. Robinson C.J Rehabilitation engineering. CRC press
1995.
Reference Book:
1. Fitting the task to human, A textbook of occupational ergonomics, 5th edition, Taylor
&Francis, ACGIH publications , 2008
2. Work study & Ergonomics by DhanpatRai& sons, 1992
3.Horia- NocholaiTeodorecu, L.C.Jain , Intelligent systems and technologies in
rehabilitation engineering; CRC; December 2000.
4. Etienne Grandjean, Harold Oldroyd, Fitting the task to the man, Taylor & Francis,1988.
Course Outcomes: On completion of this course, the students shall be able to
20
1. Understand the principles behind the ergonomics and rehabilitation engineering and
analyze the task oriented principles of ergonomics.
2. Understand the visual, augmented principles of rehabilitation engineering.
3. To demonstrate the sensory principles for various applications.
4. Demonstrate an understanding of the basic concepts of assistive devices as prosthetic
implants in ortho related applications.
ARTIFICIAL INTELLIGENCE
Subject Code: ML7PE534 Credits: 3-0-0-3
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
• To create appreciation and understanding of both the achievements of AIand the theory
underlying those achievements.
• To impart basic proficiency in representing real life problems in a state space representation so
as to solve them using different AI techniques.
• To create an understanding of the basic issues of knowledge representation and heuristic search
techniques.
UNIT I: [08 Hrs]
Introduction: What is Artificial Intelligence?, AI Problems, The underlying Assumption, What
is an AI Technique, Problems, problem spaces, and search Defining the problem as a State Space
Search, Production Systems, Problem Characteristics, Production System Characteristics, Issues
in the Design of search programs, Additional Problems.
UNIT II: [08 Hrs]
Heuristic and Search Techniques: Generate-and-Test, Hill Climbing, Best-First Search,
Problem Reduction, Constraint satisfaction, Means-Ends Analysis
UNIT III: [08 Hrs]
Knowledge Representation Issues: Representation and Mappings, Approaches to knowledge
Representation, Issues in knowledge Representation, Weak Slot Filler Structures: Semantic Nets,
Frames
UNIT IV: [08 Hrs]
Using Predicate Logic: Representing the simple facts in logic, Representing Instance and ISA
21
Relationships, Computable functions and predicates, Resolution, Natural Deduction
UNIT V: [07 Hrs]
Strong slot-and-Filter Structures : Conceptual Dependency, Scripts, CYC Expert Systems
Representation and Using Domain Knowledge, Expert Systems shells, Explanation, Knowledge
Acquisition.
Text Books:
1. Elaine Rich, Kevin Knight, Shivashankar B Nair: Artificial Intelligence, 3rd Edition, Tata
McGraw Hill, 1991.
Reference Books:
1. Stuart Russel, Peter Norvig: Artificial Intelligence A Modern Approach, 2nd Edition, Pearson
Education, 2003.
2. Nils J. Nilsson: Principles of Artificial Intelligence, Elsevier, 1980.
Course Outcomes:
On completion of this course, the students shall be able to
1. Demonstrate the knowledge of building blocks of AI.
2. Analyze and formalize the problem as a state space tree, design heuristics and solve using
different search techniques.
3. Analyze and demonstrate knowledge representation using various techniques.
4. Develop AI solutions for a given problem.
BIOMEDICAL DIGITAL SIGNAL PROCESSING LAB
Subject Code: ML7L01 Credits: 0-0-3-1.5
Duration: 3 Hr/Week
Course Objectives:
1. To understand the basic signals in the field of biomedical.
2. To study origins and characteristics of some of the most commonly used biomedical
signals, including ECG, EEG, evoked potentials, and EMG.
3. To understand Sources and characteristics of noise and artifacts in bio signals.
4. To understand use of bio signals in diagnosis, patient monitoring and physiological
investigation.
22
1. Computation of Convolution and Correlation Sequences.
2. Signal Averaging to Improve the SNR
3. Read and plotting of ECG data, spectrum of ECG with 50 HZ noise.
4. Design of FIR Filter for ECG.
5. Integer filters for ECG
6. QRS detection and Heart rate determination.
7. Correlation and Template matching.
8. Realization of Notch filter for removal of line interference
9. Data Compression Techniques using AZTEC algorithm.
10. Data Compression Techniques using TP algorithm.
11. Data Compression Techniques using FAN algorithm.
Note: The above experiments are to be conducted using Matlab/ Lab VIEW/ “C” language.
Text Books:
1. Bioelectrical Signal Processing in Cardiac & Neurological Applications - Leif SSrnmo ,
Pablo Laguna - Elsevier - Academic Press.
Reference Book:
1. Biomedical Digital Signal Processing, Willis J. Tompkins, PHI.
2. Biomedical Signal Processing- principles and techniques by D. C. Reddy, Tata McGraw-
Hill, 2005
3. Biomedical Signal Analysis by Rangaraj M. Rangayyan, IEEE Press, 2001.
Course Outcomes:
• Understand the nature of biomedical signals, objectives of signal analysis, difficulties in
biomedical signal analysis
• Different types of noise that can corrupt biomedical signals, filters used to remove
artifacts.
• Understand the processing concepts for analysis, acquisition and classification of sleep
using EEG signal.
• Understand and apply various data compression techniques on different types of
biomedical signals.
23
C++ AND PYTHON LAB
Subject Code: ML7L02 Credits: 0-0-3-1.5
Duration: 3 Hr/Week
C++ Lab:
1. Write a C++ program to calculate the sum of the series i) 1+x+x2+x3+...+xn
ii) -1+2-4+8-16+...1024
2. Write a C++ program to sort the elements of an array using i) Selection sort ii) Bubble sort
3. Write a C++ program to accept two arrays of different lengths. Merge the two accepted arrays.
4. Write a C++ program to accept two 2-dimensional arrays and perform addition, subtraction
and multiplication.
5. Write a C++ program to find the LCM and GCD of 2 given numbers using functions.
6. Write a C++ program to find the factorial of a given number using recursive function.
7. Write a C++ program to find the largest, smallest and their averages using functions.
8. Write a C++ program to accept the information about an employee and calculate the following
and display using structure.
i) Accept the basic salary, name, id_no of an employee.
ii) Calculate DA, HRA, PF, LIC, Gross and net salary.
DA: 45% of basic salary
HRA: If basic is >=2000 and <3000, HRA=800
If basic is >=3000 and <4000, HRA=1000
If basic is >=4000 and <6000, HRA=1200
If basic is >=6000, HRA=1500
PF: 11.5% of basic salary
LIC: 17% of basic salary
Gross=basic salary+DA+HRA
Net salary=Gross-PF-LIC
24
9. Write a C++ program to find the sum of two complex numbers using classes by overloading
operator +.
10. Write a C++ program to multiply two numbers using Multiple Inheritance.
Python Lab:
2. Basic programs using python:
i) Display of a word/ sentence.
ii) Performing calculations.
iii) Use of variables and objects.
iv) Use of loops, arrays, functions, plots.
Text Books:
1. Object Oriented programming in TURBO C++ ,Robert Lafore, Galgotia
Publications.2002.
2. Classic Data Structures, Debasis Samanta, Second Edition, PHI, 2009.
Reference Book:
1. Object Oriented Programming with C++ ,E.Balaguruswamy, third edition, TMH 2006
2. C++ the complete reference, Herbert Schildt, fourth edition, TMH, 2003.
Course Outcomes: By the completion of this course, the student will be able to:
• know how to use data types based on the programs and declare variables.
• Learn the concepts and importance of functions, arrays, classes & objects.
• Understand the concept of Operator Overloading and inheritance for effective
programming.
• learn the basic concepts of python.
25
NEURAL NETWORKS
Subject Code: ML8T01 Credits: 4-0-0-4
Duration: 4Hr/Week No. of Hrs: 52 Hrs
Course Objectives:
This course gives an introduction to basic neural network architectures and learning rules.
Emphasis is placed on the mathematical analysis of these networks, on methods of training them
and on their application to practical engineering problems in such areas as pattern recognition,
signals processing and control systems.
UNIT I: [10 Hrs]
Introduction: The classic neuron, Membrane potential, Action potential, Neuronal electrical
behavior, Cable Equation, Synaptic Integration. Models of Neuron, Synaptic Electrical Events,
slow potential theory of neuron, two state neurons, Feedback.
UNIT II: [11 Hrs]
Network Architectures: Single layer feed forward networks; Multilayer feed forward networks,
Recurrent Networks, Knowledge representation.
UNIT III: [10 Hrs]
Learning processes: Introduction Error correction learning, Memory based learning, Hebbian
Learning, Competitive learning.
UNIT IV: [10 Hrs]
Learning paradigms: Learning with a teacher, Learning without a teacher, Learning tasks,
Memory, Adaptation Artificial intelligence and Neural networks.
UNIT V: [11 Hrs]
Information representation in biological Systems, Distributed, Map, layered structures, Visual
system, Auditory System.
Text Books:
1. James A. Anderson—An Introduction to neural networks, 2e, PHI, 1995
2. Simon Haykin—Neural Networks, Pearson education PHI 2001.
Reference Book:
26
1. Mohammad Hasan- Fundamentals of Artificial Neural Networks, PHI, 1999
Course Outcomes: on the completion of this course the students will be able to
• The fundamental concepts of artificial neural network.
• Network architectures and its principles.
• Different learning algorithms and its applications.
• Information representation in biological system and its models.
BIOMEDICAL THERAPEUTIC EQUIPMENTS
Subject Code: ML8T02 Credits: 4-0-0-4
Duration: 4 Hr/Week No. of Hrs: 52 Hrs
Course Objectives:
The objective of this course is to introduce the students to the application of biomedical
instrumentation used in surgery. This course is to familiarize the students with physiotherapy and
electrotherapy instruments and various machines used in ICU . It includes brief study of different
types of ventilators and how to design a automated drug delivery unit depends on the
requirement of patient.
UNIT I: [10 Hrs]
Instruments for Surgery: Principles of surgical diathermy, surgical diathermy Machine, safety
aspects in electro- surgical units, surgical diathermy Analyzer.
UNIT II: [10 Hrs]
Physiotherapy and Electrotherapy Equipments: High frequency heat therapy, Shortwave
diathermy, microwave diathermy, ultrasound therapy unit, Electro diagnostic therapeutic
apparatus, pain relief through electrical Stimulation, bladder and cerebella stimulators.
UNIT III: [10 Hrs]
Haemodialysis Machine: Artificial kidney, dialyzer, Membranes for haemodialysis.
Lithotripters: Stone disease problems, lithotripter machine, extra-corporeal Shock wave therapy.
Anesthesia Machine: Need for anesthesia, anesthesia Machine
UNIT IV: [10 Hrs]
Ventilators: Artificial ventilation, ventilators, types of ventilators, ventilators terms,
classification of ventilators. Modern ventilators. Humidifiers, Nebulizers and Aspirators
27
UNIT V: [12 Hrs]
Automated Drug Delivery Systems: Infusion pumps, components of drugs infusion systems
and implantable infusion systems. Closed Loop Control Infusion Pumps.
Text Books:
1. Handbook of Biomedical Instrumentation – by R.S.Khandpur, 2 McGraw Hill, 2003.
2. Biomedical Instrumentation by Dr.M. Arumugam-Second Edition- 1994.
Course Outcomes:
• Learn the working principle of Instruments for surgery and physiotherapy, electrotherapy
instruments
• Understand the working of kidney, design of artificial kidney. Advantages and need of
anesthesia machine.
• Understand the principles of ventilators, study about different types of ventilators.
• Analyzing the concepts of Automated Drug delivery Systems.
MACHINE LEARNING
Subject Code: ML8PE313 Credits: 3-0-0-3
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
The main goal of this course is to help students learn, understand, and practice big data analytics
and machine learning approaches, which include the study of modern computing big data
technologies and scaling up machine learning techniques focusing on industry applications.
Mainly the course objectives are: conceptualization and summarization of big data and machine
learning, trivial data versus big data, big data computing technologies, machine learning
techniques, and scaling up machine learning approaches.
UNIT I: [08 Hrs]
Introduction: Introduction to machine learning, Examples of Machine Learning Applications.
Parametric regression: linear regression, polynomial regression, locally weighted regression,
numerical optimization, gradient descent, kernel methods.
28
UNIT II: [08 Hrs]
Generative learning: Gaussian parameter estimation, maximum likelihood estimation, MAP
estimation, Bayesian estimation, bias and variance of estimators, missing and noisy features,
nonparametric density estimation, Gaussian discriminant analysis, naive Bayes. Discriminative
learning: linear discrimination, logistic regression, logit and logistic functions, generalized linear
models, softmax regression.
UNIT III: [08 Hrs]
Neural networks: the perceptron algorithm, multilayer perceptrons, backpropagation, nonlinear
regression, multiclass discrimination, training procedures, localized network structure,
dimensionality reduction interpretation.
Support vector machines: functional and geometric margins, optimum margin classifier,
constrained optimization, Lagrange multipliers, primal/dual problems, KKT conditions, dual of
the optimum margin classifier, soft margins, kernels, quadratic programming, SMO algorithm.
UNIT IV: [07 Hrs]
Graphical and sequential models: Bayesian networks, conditional independence, Markov random
fields, inference in graphical models, belief propagation, Markov models, hidden Markov
models, decoding states from observations, learning HMM parameters.
UNIT V: [08 Hrs]
Unsupervised learning: K-means clustering, expectation maximization, Gaussian mixture density
estimation, mixture of naive Bayes, model selection. Dimensionality reduction: feature selection,
principal component analysis, linear discriminant analysis, factor analysis, independent
component analysis, multidimensional scaling, and manifold learning.
Text Books:
1). Elements of Statistical Learning, T. Hastie, R. Tibshirani and J. Friedman, Springer, 2001. 2).
Machine Learning, EthemAlpaydin, MIT Press, 2010.
.
Reference Books :
1). Pattern Recognition and Machine Learning, C. Bishop, Springer, 2006.
2). Machine Learning: A Probabilistic Perspective, K. Murphy, MIT Press, 2012.
3). Pattern Classification, R. Duda, E. Hart, and D. Stork, Wiley-Interscience, 2000.
29
4). Machine Learning, T. Mitchell, McGraw-Hill, 1997.
Course Outcomes:
• Apply the knowledge of mathematics science and engineering fundamentals in the
understanding of fundamental issues and challenges of machine learning: data, model
selection, model complexity, etc.
• Analyze the strengths and weaknesses of many popular machine learning approaches.
• Comprehend the underlying mathematical relationships within and across Machine
Learning algorithms and the paradigms of supervised and un-supervised learning.
• Design and implement various machine learning algorithms in a range of real-world
applications.
SMART WEARABLE SYSTEMS
Subject Code: ML8PE312 Credits: 3-0-0-3
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
Extensive efforts have been made in both academia and industry in the research and development
of smart wearable systems (SWS) for health monitoring (HM). Primarily influenced by
skyrocketing healthcare costs and supported by recent technological advances in micro- and
nanotechnologies, miniaturisation of sensors, and smart fabrics, the continuous advances in SWS
will progressively change the landscape of healthcare by allowing individual management and
continuous monitoring of a patient’s health status. Consisting of various components and
devices, ranging from sensors and actuators to multimedia devices, these systems support
complex healthcare applications and enable low-cost wearable, non-invasive alternatives for
continuous 24-h monitoring of health, activity, mobility, and mental status, both indoors and
outdoors. Our objective has been to examine the current research in wearable to serve as
references for researchers and provide perspectives for future research
UNIT I: [08 Hrs]
Introduction : What is Wearable Systems, Need for Wearable Systems, Drawbacks of
Conventional Systems for Wearable Monitoring, Applications of Wearable Systems, Recent
developments – Global and Indian Scenario, Types of Wearable Systems, Components of
wearable Systems, Physiological Parameters commonly monitored in wearable applications,
Smart textiles, & textiles sensors, Wearable Systems for Disaster management, Home Health
care, Astronauts, Soldiers in battle field, athletes, SIDS, Sleep Apnea Monitoring.
30
UNIT II: [08 Hrs]
Smart Sensors& Vital Parameters : Vital parameters monitored and their significances, Bio-
potential signal recordings (ECG, EEG, EMG), Dry Electrodes design and fabrication methods,
Smart Sensors – textile electrodes, polymer electrodes, non-contact electrodes, MEMS and Nano
Electrode Arrays, Cuff-less Blood Pressure Measurement, PPG, Galvanic Skin Response (GSR),
Body Temperature Measurements, Activity Monitoring for Energy Expenditure, Respiratory
parameters.
UNIT III: [08 Hrs]
Wearable Computers : Flexible Electronics, Wearable Computers, Signal Processors, Signal
Conditioning circuits design, Power Requirements, Wearable Systems Packaging, Batteries and
charging, Wireless Communication Technologies and Protocols, Receiver Systems, Mobile
Applications based devices.
UNIT IV: [07 Hrs]
Wireless Body Area Networks: Wireless Body Area Networks – Introduction, Personal Area
Networks (PAN), Application in Vital Physiological Parameter monitoring, Design of Sensor &
Sink Nodes, Architecture, Communication & Routing Protocols, Security, Power and Energy
Harvesting.
UNIT V: [08 Hrs]
Data Processing And Validation : Classification Algorithms, Data Mining and Data Fusion,
Signal Processing Algorithms in wearable Applications, Issues of wearable physiological
monitoring systems, Statistical Validation of Parameters, Certifications of Medical Devices and
Patenting.
Text Books:
1. Annalisa Bonfiglo, Danilo De Rossi, Wearable Monitoring Systems, Springer, 2011
2. Edward Sazonov, Micheal R Neuman, Wearable Sensors: Fundamentals, Implementation and
Applications, Elseiver, 2014.
Reference Books:
1. Kate Hartman, Make: Wearable Electronics: Design, Prototype and wear your own interactive
garments, Maker Media
2. Elijah Hunter, Wearable Technology, Kindle Edition
3. Guang Zhong Yang, Body Sensor Networks, Springer .
Course Outcomes: On completion of this course, the students shall be able to
1. Understand the basic foundations on biological and artificial neural network and the
importance of neuron models for pattern classification
2. Demonstrate the process of forming association between related patterns through associative
networks
31
3. Apply the principles of back propagation supervised learning for error minimization
4. Understand and analyze the various competition based learning algorithms and importance of
resonance based network learning algorithms.
SPEECH SIGNAL PROCESSING
Subject Code: ML8PE311 Credits: 3-0-0-3
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
i) To understand the characteristics of speech signal,
ii) To apply signal processing concepts to speech signal,
iii) To get an insight into a few applications of speech processing.
UNIT I: [08 Hrs]
Digital Models For Speech Signals: Process of Speech Production, Lossless tube models,
Digital models for Speech signals.
Time Domain Models For Speech Processing: Time dependent processing of speech, Short
time energy and average magnitude, Short time average zero crossing rate, Speech Vs silence
discrimination using energy and zero crossing.
UNIT II: [08 Hrs]
Short Time Fourier Analysis: Linear filtering interpretation, Filter bank summation method,
Design of digital filter banks, Implementation using FFT, Spectrographic displays.
UNIT III: [08 Hrs]
Digital Representations Of The Speech Waveform: Sampling speech signals, Review of the
statistical model for speech, Instantaneous quantization, Adaptive Quantization, General theory
of differential quantization, Delta modulation.
UNIT IV: [07 Hrs]
Linear Predictive Coding Of Speech: Basic principles of linear predictive analysis, Solution of
LPC equations, Prediction error signal, Frequency domain interpretation, Relation between the
various speech parameters, Applications of LPC parameters.
32
UNIT V: [08 Hrs]
Speech Synthesis: Principles of Speech synthesis, Synthesis based on waveform coding,
analysis synthesis method, speech production mechanism, Synthesis by rule, Text to speech
conversion.
Speech Recognition: Principles of Speech recognition, Speech period detection, Spectral
distance measures, Structure of word recognition systems, Dynamic time warping (DTW), Word
recognition using phoneme units.
Text Books:
1. Digital Processing of Speech Signals- L R Rabiner and R W Schafer, Pearson
Education 2004.
2. Digital Speech Processing- Synthesis and Recognition, Sadoaki Furui, 2nd
Edition, Mercel Dekker 2002.
.
Reference Books:
1. Introduction to Data Compression- Khalid Sayood, 3rd Edition, Elsivier
Publications.
2. Digital Speech-A M Kondoz, 2nd Edition, Wiley Publications
Course Outcomes: On completion of the course the student can recall
• Properties of speech signal and its production and discrimination system
• Design of filter bank and its implementation, and spectrographic display.
• Digital representation of speech signal using different quantization techniques.
• LPC algorithms and its applications for speech coding and fundamental algorithms for
speech synthesis, coding and recognition.
33
CLINICAL DATA ANALYTICS
Subject Code: ML8PE314 Credits: 3-0-0-3
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
• Identify key tools and approaches to improve analytics capabilities in clinical settings.
• Describe different governance and operations strategies in analytics in clinical settings.
• Discuss value-based payment systems and the role of data analytics in achieving their potential.
• Analyze data used in population management and value-based care systems.
UNIT I: [08 hours]
Introduction to Biostatistics: Introduction, Some basic concepts, Measurement and
Measurement Scales, Simple random sample, Computers and biostatistician analysis. Descriptive
Statistics: Introduction, ordered array, grouped data-frequency distribution, descriptive statistics
– measure of central tendency, measure of dispersion, measure of central tendency probability
distributions of discrete variables, binomial distribution, Poisson distribution, continuous
probability distribution, normal distribution.
UNIT II: [08 hours]
Sampling distributions: distribution of sample mean, distribution of the difference between two
sample means, distribution of sample proportion, distribution of the difference between two
sample proportions, Estimation: confidence interval for a population mean, t-distribution,
confidence interval for differences between two population means, confidence interval for a
population proportion, confidence interval for difference between two populations determination
of sample size for estimating means, for estimating proportions , confidence interval for the
variance of normally distributed population, confidence interval for ratio of variances of two
normally distributed populations.
UNIT III: [07 hours]
Hypothesis Testing : Introduction, hypothesis testing – single population mean, difference
between two population means, paired comparisons, hypothesis testing-single population
proportion, difference between two population proportions, single population variance, ratio of
two population variances.
34
UNIT IV: [08 Hrs]
Analysis of Variance (ANOVA): Introduction, completely randomized design, randomized
complete block design, repeated measures design, factorial experiment UNIT-5 8 hours Linear
Regression and Correlation: the regression model, sample regression equation, evaluating and
using regression equation, correlation model correlation coefficient Multiple linear regression
model, obtaining multiple regression equation, evaluating multiple regression equation, using the
multiple regression equation, multiple correlation model, mathematical properties of Chisquare
distribution.
UNIT V: [08 Hrs]
Linear Regression and Correlation: the regression model, sample regression equation, evaluating
and using regression equation, correlation model correlation coefficient Multiple linear
regression model, obtaining multiple regression equation, evaluating multiple regression
equation, using the multiple regression equation, multiple correlation model, mathematical
properties of Chi-square distribution.
Text Books:
1. 1. “Biostatistics-A Foundation for Analysis in the Health Sciences” Wayne W. Daniel, John
Wiley & Sons Publication, 6th Edition
2. Fundamentals of Biiostatistics by khan and khanum, Ukaaz publications, 2nd revise edition
3. “An introduction to statistical Method and data analysis”, by R. Lyman ott..
Course Outcomes:
• Ability to apply knowledge of mathematics, science and Engineering to develop the
solution using biostatistical concepts.
• Ability to analyse a problem and formulate appropriate solution for biostatistical concepts
application.
• An ability to design and perform statistical test and interpret results
• Ability to implement and demonstrate statistical analysis using modern tool usage.
ARM PROCESSORS
Subject Code: ML8PE411 Credits: 3-0-0-3
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
• This course introduces the concept of architecture and programming of advanced
embedded microcontrollers i.eARMfamily of microcontrollers that are widely used in
design of real time sophisticated embedded systems like tablets, hand held devices,
35
automation and industrial control systems.
• It also covers writing Embedded C programming of LPC2148 for GPIO,ADC,DAC,
UART, LCD, Timers and etc.
• It also explains the concepts of embedded system and its components.
UNIT I: [08 Hrs]
ARM EMBEDDED SYSTEMS
The RISC Design Philosophy, The ARM Design Philosophy, Embedded System Hardware,
Embedded System Software.
ARM PROCESSOR FUNDAMENTALS
Registers, Current Program Status Register, Pipeline, Exceptions, Interrupts, and Vector Table,
Core Extensions, Architecture Revisions, ARM Processor Families, LPC2148 Microcontroller
Architecture, Memory Mapping, Register Description.
UNIT II: [07 Hrs]
INTRODUCTION TO THE ARM INSTRUCTIONS SET
Data Processing Instructions, Branch Instructions, Load-Store Instructions, Software Interrupt
Instructions, Program Status Register Instruction, Example Programs.
UNIT III: [08 Hrs]
INTRODUCTION TO THE ARM INSTRUCTIONS SET contd….
Loading Constants, ARMv5E Extensions, Conditional Execution, and Example Programs.
EFFICIENT C PROGRAMMING
Overview of C Compilers and Optimization, Basic C Data Types, C Looping Structures, Register
Allocation, Function Calls, Pointer Aliasing, Structure Arrangement, Bit-fields, Unaligned Data
and Endianness, Division, Floating Point, Inline Functions and Inline Assembly.
UNIT IV: [08 Hrs]
Interfacing
Sensors, Actuators, GPIO, LED, 7 segment display, stepper motor, Keyboard, Push button
switch, Data Conversions (ADC, DAC), Timers, Communication Protocols: UART, I2C, SPI,
CAN(onboard), Programs using C.
UNIT V: [08 Hrs]
Embedded System Components
Embedded v/s General computing system, Classification of Embedded systems, Major
applications and purpose of Embedded systems. Core of an Embedded System including all
types of processor/controller, Memory.
Text Books:
1.ARM Systems Developer's Guide Designing and Optimizing System Software, Andrew N.
Sloss, Dominic Symes, Chris Wright, Morgan Kaufmann Publishers, ElseveirInc,
2004.(Chapters 1, 2, 3, 5)
2. Introduction to Embedded Systems, Shibu K V, Secondedition, Tata McGraw Hill Education
Private Limited, 2017. (Chapters 1 and 2 selected topics)
3.LPC214x User Manual –
http://www.keil.com/dd/docs/datashts/philips/user_manual_lpc214x.pdf
36
(LPC2148, GPIO, Registers, Embedded components selected)
Reference Books:
1. ARM System On Chip Architecture, Steve Furber, Second Edition, Pearson Education
Limited, 2000.
2. ARM ASSEMBLY LANGUAGE Fundamentals and Techniques, WilliamHohl, Christopher
Hinds, Second Edition, CRC Press, 2015.
3. ARM Assembly Language An Introduction, Gibson, Second Edition, 2007.
Course Outcomes:
• Describe the ARM processor architecture and its family.
• Develop assembly language programs to perform specific tasks using ARM instructions.
• Develop ARM microcontroller applications using Embedded C language.
• Design and develop program to interface external hardware with LPC214x
microcontroller.
ROBOTICS AND AUTOMATION
Subject Code: ML8PE412 Credits: 3-0-0-3
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
This course introduces fundamental concepts in robotics. The objective of the course is to
provide an introductory understanding of robotics. Students will be exposed to a broad range of
topics in robotics with emphasis on basics of manipulators, coordinate transformation and
kinematics, trajectory planning, control techniques, sensors and devices, robot applications and
economics analysis.
UNIT I: [08 Hrs]
BASIC CONCEPTS Automation and Robotics – An over view of Robotics – present and future
applications – classification by coordinate system and control system, Hydraulic, Pneumatic and
electric drivers – Determination HP of motor and gearing ratio.
UNIT II: [08 Hrs]
MANIPULATORS: Construction of Manipulators, Manipulator Dynamic and Force Control,
Electronic and Pneumatic manupulators.
37
ACTUATORS AND GRIPPERS Pneumatic, Hydraulic Actuators, Stepper Motor Control
Circuits, End Effecter, Various types of Grippers.
UNIT III: [07 Hrs]
TRANSFORMATION AND DYNAMICS Differential transformation and manipulators,
Jacobians – problems.Dynamics: Lagrange – Euler and Newton – Euler formations.
UNIT IV: [08 Hrs]
KINEMATICS Forward and Inverse Kinematic Problems, Solutions of Inverse Kinematic
problems,Multiple Solution, Jacobian Work Envelop – Hill Climbing Techniques.
UNIT V: [08 Hrs]
PATH PLANNING Trajectory planning and avoidance of obstacles, path planning, skew
motion, joint integrated motion – straight-line motion.
Text Books:
1. Industrial Robotics / Groover M P /Pearson Edu.
2. Fu, K.S., Gonzalez, R.C., and Lee, C.S.G., Robotics control, Sensing, Vision and
Intelligence, McGraw-Hill Publishing company, New Delhi, 2003.
3. Klafter, R.D., Chmielewski, T.A., and Negin. M, Robot Engineering-An Integrated
Approach, Prentice Hall of India, New Delhi, 2002.
4. Craig, J.J., Introduction to Robotics Mechanics and Control, Addison Wesley, 1999.
Reference Books:
1. Robotics, CSP Rao and V.V. Reddy, Pearson Publications (In press)
2. An Introduction to Robot Technology, P. Coiffet and M. Chaironze Kogam
3. Robot Analysis and Intelligence Asada and Slow time Wiley Inter-Science.
4. Robot Dynamics and Control by Mark W. Spong and M. Vidyasagar, JohnPage Ltd.
1983 London.Wiley & Sons..
Course Outcomes: 1. Understand the fundamental concepts of robot
38
2. Calculate the forward kinematics and inverse kinematics of serial and parallel robots.
3. Be able to calculate the Jacobian for serial and parallel robot.
4. Be able to do the path planning for a robotic system.
MEDICAL DEVICE DEVELOPMENT
Subject Code: ML8PE413 Credits: 3-0-0-3
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
• Understand the processes for medical device development after “design freeze”
• Become familiar with the European regulatory framework for medical devices
• Gain an understanding of manufacturing process validation
• Build on the student’s current understanding of the Quality Management System
• Understand key aspects of Product Management both during and after product launch
• Discuss Good Clinical Practices and regulations surrounding management of clinical
trials
UNIT I: [10 Hrs]
MedTech Invention: Needs finding through Observation and Problem Identification. Need
Statement Development. Need Screening & Selection through Stakeholder Analysis, Market
Analysis & Needs Filtering. Concept Generation, Screening and selection.
UNIT II: [07 Hrs]
Product Requirements: Define MedTech Device. Classification of Device. Role of
Requirements in MedTech Product Development. Market Requirements, Customer
Requirements, Clinical Workflow. Design Input. ISO 13485. Intended use, Functional /
performance requirements, safety, usability requirements etc.....
UNIT III [8 hours]
Design Engineering: Design and Development Plan. Design Process. Design Outputs,
Intermediate deliverables - System Architecture, Subsystem requirements, Prototype, System
Integration. Design Review. Design Verification.
39
UNIT IV [7 hours]
Validation: System Validation. Usability Validation. Safety Validation. Clinical Validation,
Regulatory Submission UNIT V [6 hours] Program Management: Program Planning, Stage Gate
Process, Milestones. Budgeting, Development Strategy, Risk identification and Mitigation
process.
UNIT V: [06 Hrs]
Program Management: Program Planning, Stage Gate Process, Milestones. Budgeting,
Development Strategy, Risk identification and Mitigation process.
Text Books:
1. “Biodesign: The Process of Innovating Medical Technologies”, by Stefanos Zenios , Josh
Makower, Paul Yock, Todd J. Brinton, Uday N. Kumar, Lyn Denend, Thomas M. Krummel
published by Cambridge University Press; 2nd edition.
Reference Books:
1. “Inventing medical devices: A perspective from India”, by Dr Jagdish Chaturvedi,
CreateSpace Independent Publishing Platform; 1st edition, 2015.
2. “The Medical Device R&D Handbook”, by Theodore R. Kucklick, Second Edition, CRC
Press, 2012.
Course Outcomes:
• Identify and analyse unmet clinical need and its requirements to solve it.
• Search, analyse and document clinical practice, engineering science and relevant
literature in order to determine the need for further research and development in a chosen
clinical area.
• Develop a sustainable business plan, including market overview, regulation strategies for
health & safety of individuals and intellectual property (IP) strategies.
• . Understand medical device design engineering and manufacturing process by avoiding
common quality pitfalls in turn learning project management.
VIRTUAL BMI
Subject Code: ML8PE414 Credits: 3-0-0-3
40
Duration: 3 Hr/Week No. of Hrs: 39 Hrs
Course Objectives:
The main goal of this course is for students to learn applications of programming, signal
transduction, data acquisition, data analysis, and signal processing used in the design of medical
and laboratory instrumentation. The software package LabVIEW has become a standard in
academic and industrial environments for data acquisition, interfacing of instruments and
instrumentation control. Students will learn LabVIEW as a tool for the design of computer-based
virtual instruments, which add software-based intelligence to sensors and basic laboratory bench
devices.
UNIT I: [07 Hrs]
Graphical System Design (GSD): Introduction, GSD model, Design flow with GSD, Virtual
Instrumentation, Virtual Instrumentation and traditional instrumentation, Hardware and software
in virtual instrumentation, Virtual Instrumentation for test, control and design, GSD using
LabVIEW, Graphical programming and textural programming. Introduction to LabVIEW:
Introduction, Advantages of LabVIEW, Advantages of LabVIEW, Software environment,
Creating and saving a VI, Front panel toolbar, Block diagram toolbar, Palettes, Shortcut menus,
Property dialog boxes, Front panel controls and indicators, Block diagram, Data types, Data flow
program, LabVIEW documentation resources, Keyword shortcuts.
UNIT II: [08 Hrs]
Modular Programming: Introduction, Modular Programming in LabVIEW, Build a VI front
panel and block diagram, ICON and connector pane, Creating an icon, Building a connector
pane, Displaying subVIs and express Vis as icons or expandable nodes, Creating subVIs from
sections of a VI, Opening and editing subVIs, Placing subVIs on block diagrams, Saving subVIs,
Creating a stand-alone application. Data Acquisition: DAQ software architecture, DAQ assistant,
Channels and task configurations, Selecting and configuring a data acquisition device,
Components of computer based measurement system.
UNIT III: [08 Hrs]
General Goals of Virtual Bio-Instrumentation (VBI): Definition of VBI and importance,
General Goals of VBI applications. Basic Concepts: DAQ basics, LabVIEW basics, BioBench
basics. Neuromuscular Electrophysiology (Electromyography): Physiological basis, Experiment
set up, Experiment descriptions, Trouble shooting the nerve –Muscle Preparation. Cardiac
Electrophysiology (Electrocardiology):Physiological basis, Experiment descriptions.
Cardiopulmonary Applications: Cardiopulmonary measurement system, Hiw the
Cardiopulmonary measurement system works, Clinical Significance.
UNIT IV: [08 Hrs]
Medical Device Development Applications: The Endotester – A Virtual Instrument –Based
Quality control and Technology, Assessment System for surgicalvideoSystems: Introduction,
Materials and Methods, Endoscope Tests, Results, Discussion. Fluid Sense Innovative IV Pump
Testing: Introduction, The test System, Training Emulator.
UNIT V: [08 Hrs]
41
Healthcare Information management Systems: Medical Informatics: Defining medical
informatics, Computers in medicine, Electronic Medical record, Computerized physician order
entry, Decision support. Information Retrieval, Medical Imaging, Patient Monitoring, Medical
Education, Medical Simulation. Managing Disparate Information: ActiveX, ActiveX Data
Objects(ADO), Dynamic Link Libraries, Database Connectivity, Integrated Dashboards.
Text Books:
1. Virtual Instrumentation using LabVIEW by Jovitha Jerome, PHI Learning Private Limited,
2010. (Module 1 & 2)
2. “Virtual Bio-Instrumentation” Biomedical, Clinical, and Healthcare Applications in Lab
VIEW. ,by Jon B. Olansen and Eric Rosow, Prentice Hall Publication, 2002.
Course Outcomes:
1. Describe the Graphical System Design approach & basic features and techniques of Lab
VIEW.
2. Use the Modular Programming concepts for creation of VIs & employ DAQ assistant for
configuration of hardware devices.
3. Describe the Lab VIEW and BioBench software for EMG, ECG, and Cardiopulmonary system
analysis.
4. Explain the Medical Device Development Applications for Surgical Video Systems and
Healthcare Information Management Systems using Information Science and Technology.
Project Work-Phase-1
Code: ML7PW01 Credits: 0-0-8-4
Phase-1- Literature survey/synopsis/Seminar --4 Credits 50 M
Project Work-Phase-II
Code: ML8PW02 Credits: 0-0-8-4
Phase II - --------- 10 Credits
Project Presentation+ Project Report + Internal Viva --- 5Credits --- 100M External Viva (Demonstration +Desertation+Seminar+Vivavoce) --- 5 Credits --- 100M
Technical Seminar
Code: ML8TS01 Credits: 0-0-2-1
Seminar/Report --1 Credits 50 M
Students are required to present a technical seminar on advanced trends in biomedical field and provide
a detailed report on the same.